SOTAVerified

Image Generation

Image Generation (synthesis) is the task of generating new images from an existing dataset.

  • Unconditional generation refers to generating samples unconditionally from the dataset, i.e. $p(y)$
  • Conditional image generation (subtask) refers to generating samples conditionally from the dataset, based on a label, i.e. $p(y|x)$.

In this section, you can find state-of-the-art leaderboards for unconditional generation. For conditional generation, and other types of image generations, refer to the subtasks.

( Image credit: StyleGAN )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 4501–4550 of 6689 papers

TitleStatusHype
How Image Generation Helps Visible-to-Infrared Person Re-Identification?—0
Red-Teaming the Stable Diffusion Safety Filter—0
Membership Inference Attacks Against Text-to-image Generation Models—0
From Face to Natural Image: Learning Real Degradation for Blind Image Super-ResolutionCode1
Improving Sample Quality of Diffusion Models Using Self-Attention GuidanceCode7
Visual Prompt Tuning for Generative Transfer LearningCode1
Generated Faces in the Wild: Quantitative Comparison of Stable Diffusion, Midjourney and DALL-E 2Code1
Pixel-Level BPE for Auto-Regressive Image Generation—0
T2CI-GAN: Text to Compressed Image generation using Generative Adversarial Network—0
Multi-objective Deep Data Generation with Correlated Property ControlCode0
Building Normalizing Flows with Stochastic InterpolantsCode2
Improving 3D-aware Image Synthesis with A Geometry-aware Discriminator—0
S2P: State-conditioned Image Synthesis for Data Augmentation in Offline Reinforcement LearningCode0
Make-A-Video: Text-to-Video Generation without Text-Video DataCode1
Creative Painting with Latent Diffusion Models—0
Re-Imagen: Retrieval-Augmented Text-to-Image Generator—0
Denoising MCMC for Accelerating Diffusion-Based Generative ModelsCode1
DreamFusion: Text-to-3D using 2D DiffusionCode5
Discrete Predictor-Corrector Diffusion Models for Image Synthesis—0
Compressed Gastric Image Generation Based on Soft-Label Dataset Distillation for Medical Data Sharing—0
Adma-GAN: Attribute-Driven Memory Augmented GANs for Text-to-Image Generation—0
Data Augmentation using Feature Generation for Volumetric Medical Images—0
medigan: a Python library of pretrained generative models for medical image synthesisCode1
What Does DALL-E 2 Know About Radiology?—0
Activation Learning by Local Competitions—0
On Investigating the Conservative Property of Score-Based Generative ModelsCode0
Personalizing Text-to-Image Generation via Aesthetic GradientsCode2
All are Worth Words: A ViT Backbone for Diffusion ModelsCode3
Conversion Between CT and MRI Images Using Diffusion and Score-Matching Models—0
MAGIC: Mask-Guided Image Synthesis by Inverting a Quasi-Robust ClassifierCode0
Implementing and Experimenting with Diffusion Models for Text-to-Image GenerationCode0
Poisson Flow Generative ModelsCode2
Improving GANs with A Dynamic Discriminator—0
Exploiting Cultural Biases via Homoglyphs in Text-to-Image SynthesisCode1
Adaptive Multi-stage Density Ratio Estimation for Learning Latent Space Energy-based Model—0
MoVQ: Modulating Quantized Vectors for High-Fidelity Image GenerationCode5
Can segmentation models be trained with fully synthetically generated data?—0
Towards Bridging the Performance Gaps of Joint Energy-based ModelsCode0
Exploring StyleGAN Latent Space for Face Alignment with Limited Training Data—0
One-Shot Synthesis of Images and Segmentation MasksCode1
Langevin Autoencoders for Learning Deep Latent Variable ModelsCode0
DEANet: Decomposition Enhancement and Adjustment Network for Low-Light Image Enhancement—0
Weakly-Supervised Stitching Network for Real-World Panoramic Image Generation—0
StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story ContinuationCode0
3DFaceShop: Explicitly Controllable 3D-Aware Portrait GenerationCode2
Soft Diffusion: Score Matching for General Corruptions—0
Use Classifier as GeneratorCode0
Improved Masked Image Generation with Token-Critic—0
Pathology Synthesis of 3D-Consistent Cardiac MR Images using 2D VAEs and GANsCode0
Generative Deformable Radiance Fields for Disentangled Image Synthesis of Topology-Varying Objects—0
Show:102550
← PrevPage 91 of 134Next →
All datasetsImageNet 256x256CIFAR-10ImageNet 64x64ImageNet 512x512FFHQ 256 x 256CelebA 64x64ImageNet 32x32LSUN Bedroom 256 x 256STL-10LSUN Churches 256 x 256ImageNet 128x128FFHQ 1024 x 1024

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Improved DDPMFID12.3—Unverified
2ADMFID11.84—Unverified
3BigGAN-deepFID8.1—Unverified
4Polarity-BigGANFID6.82—Unverified
5VQGAN+Transformer (k=mixed, p=1.0, a=0.005)FID6.59—Unverified
6MaskGITFID6.18—Unverified
7VQGAN+Transformer (k=600, p=1.0, a=0.05)FID5.2—Unverified
8CDMFID4.88—Unverified
9ADM-GFID4.59—Unverified
10RINFID4.51—Unverified
#ModelMetricClaimedVerifiedStatus
1PresGANFID52.2—Unverified
2RESFLOWFID48.29—Unverified
3Residual FlowFID46.37—Unverified
4GLF+perceptual loss (ours)FID44.6—Unverified
5ProdPoly no activation functionsFID40.45—Unverified
6ProdPoly no activation functionsFID36.77—Unverified
7ACGANFID35.47—Unverified
8DenseFlow-74-10FID34.9—Unverified
9NVAE w/ flowFID32.53—Unverified
10QSNGANFID31.97—Unverified
#ModelMetricClaimedVerifiedStatus
1GLIDE + CLSFID30.87—Unverified
2GLIDE + CLIPFID30.46—Unverified
3GLIDE + CLS-FREEFID29.22—Unverified
4GLIDE + CLIP + CLS + CLS-FREEFID29.18—Unverified
5PGMGANFID21.73—Unverified
6CLR-GANFID20.27—Unverified
7FMFID14.45—Unverified
8CT (Direct Generation, NFE=1)FID13—Unverified
9CT (Direct Generation, NFE=2)FID11.1—Unverified
10GLIDE +CLSKID7.95—Unverified